Papers
Thu 10 Mar 2022
160 papers
- Conditional Prompt Learning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Prediction-Guided Distillation for Dense Object DetectionKnowledge distillation → Detection and dense prediction distillation
- Look Backward and Forward: Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine TranslationKnowledge distillation → Knowledge distillation for LLMs
- Membership Privacy Protection for Image Translation Models via Adversarial Knowledge DistillationLLM safety and security → Membership inference attacks +1
- Suspected Object Matters: Rethinking Model's Prediction for One-stage Visual GroundingLLM reasoning → Multimodal reasoning
- Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better TransferabilityKnowledge distillation → General knowledge distillation methods
- Improving Neural ODEs via Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- State of the Art in Artificial Intelligence applied to the Legal Domain
- A multimodal approach for Parkinson disease analysis
- AI Annotated Recommendations in an Efficient Visual Learning Environment with Emphasis on YouTube (AI-EVL)
- HiSA-SMFM: Historical and Sentiment Analysis based Stock Market Forecasting Model
- Web Mining to Inform Locations of Charging Stations for Electric Vehicles
- Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic case
- Strategy Complexity of Point Payoff, Mean Payoff and Total Payoff Objectives in Countable MDPs
- Compressing CNN Kernels for Videos Using Tucker Decompositions: Towards Lightweight CNN Applications
- Climate Change & Computer Audition: A Call to Action and Overview on Audio Intelligence to Help Save the Planet
- Multi-Channel Convolutional Analysis Operator Learning for Dual-Energy CT Reconstruction
- Human-Like Navigation Behavior: A Statistical Evaluation Framework
- Random Ensemble Reinforcement Learning for Traffic Signal Control
- Policy Architectures for Compositional Generalization in Control
- Label-efficient Hybrid-supervised Learning for Medical Image Segmentation
- Tactile-Sensitive NewtonianVAE for High-Accuracy Industrial Connector Insertion
- Balancing Consumer and Business Value of Recommender Systems: A Simulation-based Analysis
- PC-SwinMorph: Patch Representation for Unsupervised Medical Image Registration and Segmentation
- Deep Multimodal Guidance for Medical Image Classification
- Leveraging Labeling Representations in Uncertainty-based Semi-supervised Segmentation
- The Overlooked Classifier in Human-Object Interaction Recognition
- Fusion of Sentiment and Asset Price Predictions for Portfolio Optimization
- Point Density-Aware Voxels for LiDAR 3D Object Detection
- NELA-GT-2022: A Large Multi-Labelled News Dataset for The Study of Misinformation in News Articles
- Attack Analysis of Face Recognition Authentication Systems Using Fast Gradient Sign Method
- BASIL: Balanced Active Semi-supervised Learning for Class Imbalanced Datasets
- Contextualized Sensorimotor Norms: multi-dimensional measures of sensorimotor strength for ambiguous English words, in context
- Koopman Methods for Estimation of Animal Motions over Unknown Submanifolds
- Parameter-Free Attentive Scoring for Speaker Verification
- High Definition, Inexpensive, Underwater Mapping
- PETR: Position Embedding Transformation for Multi-View 3D Object Detection
- A Linearithmic Time Locally Optimal Algorithm for the Multiway Number Partition Optimization
- City-wide Street-to-Satellite Image Geolocalization of a Mobile Ground Agent
- Deep Learning-Based Perceptual Stimulus Encoder for Bionic Vision
- Gesture based Arabic Sign Language Recognition for Impaired People based on Convolution Neural Network
- Human Face Recognition from Part of a Facial Image based on Image Stitching
- A new approach to calculating BERTScore for automatic assessment of translation quality
- On-the-Fly Test-time Adaptation for Medical Image Segmentation
- Self Pre-training with Masked Autoencoders for Medical Image Classification and Segmentation
- Deep Convolutional Neural Networks for Molecular Subtyping of Gliomas Using Magnetic Resonance Imaging
- neos: End-to-End-Optimised Summary Statistics for High Energy Physics
- Autofocusing+: Noise-Resilient Motion Correction in Magnetic Resonance Imaging
- Unfolded Deep Kernel Estimation for Blind Image Super-resolution
- Recovering medical images from CT film photos
- SUPERNOVA: Automating Test Selection and Defect Prevention in AAA Video Games Using Risk Based Testing and Machine Learning
- LiftReg: Limited Angle 2D/3D Deformable Registration
- On Embeddings for Numerical Features in Tabular Deep Learning
- Transfer of Representations to Video Label Propagation: Implementation Factors Matter
- Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection
- Context is Everything: Implicit Identification for Dynamics Adaptation
- AGCN: Augmented Graph Convolutional Network for Lifelong Multi-label Image Recognition
- SoftSNN: Low-Cost Fault Tolerance for Spiking Neural Network Accelerators under Soft Errors
- Data-driven Abstractions with Probabilistic Guarantees for Linear PETC Systems
- Towards Less Constrained Macro-Neural Architecture Search
- An Empirical Study of Low Precision Quantization for TinyML
- Geometric and Topological Inference for Deep Representations of Complex Networks
- projUNN: efficient method for training deep networks with unitary matrices
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
- Fully Adaptive Composition in Differential Privacy
- CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization
- LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval
- Artificial Intelligence in Vehicular Wireless Networks: A Case Study Using ns-3
- Bias-variance decomposition of overparameterized regression with random linear features
- IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages
- Near-optimal Deep Reinforcement Learning Policies from Data for Zone Temperature Control
- Semantic Norm Recognition and its application to Portuguese Law
- Deep Regression Ensembles
- OneRel:Joint Entity and Relation Extraction with One Module in One Step
- Attacks as Defenses: Designing Robust Audio CAPTCHAs Using Attacks on Automatic Speech Recognition Systems
- Blind Extraction of Equitable Partitions from Graph Signals
- Robustness Analysis of Classification Using Recurrent Neural Networks with Perturbed Sequential Input
- Representation Compensation Networks for Continual Semantic Segmentation
- Asymptotic Bounds for Smoothness Parameter Estimates in Gaussian Process Interpolation
- Annotation Efficient Person Re-Identification with Diverse Cluster-Based Pair Selection
- Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation
- KSoF: The Kassel State of Fluency Dataset -- A Therapy Centered Dataset of Stuttering
- Spatial Commonsense Graph for Object Localisation in Partial Scenes
- Forecasting the abnormal events at well drilling with machine learning
- A Contribution-based Device Selection Scheme in Federated Learning
- Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)
- SATLab at SemEval-2022 Task 4: Trying to Detect Patronizing and Condescending Language with only Character and Word N-grams
- Temporal Context for Robust Maritime Obstacle Detection
- Two-stream Hierarchical Similarity Reasoning for Image-text Matching
- Knowledge-enriched Attention Network with Group-wise Semantic for Visual Storytelling
- EyeLoveGAN: Exploiting domain-shifts to boost network learning with cycleGANs
- Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing
- TrueType Transformer: Character and Font Style Recognition in Outline Format
- Parsimonious Physics-Informed Random Projection Neural Networks for Initial-Value Problems of ODEs and index-1 DAEs
- Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesis
- Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless Objects
- SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning
- Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
- AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First -- Using Relation Extraction to Identify Entities
- Exploiting the Potential of Datasets: A Data-Centric Approach for Model Robustness
All 160
- StyleBabel: Artistic Style Tagging and Captioning
- SoK: On the Semantic AI Security in Autonomous Driving
- GrainSpace: A Large-scale Dataset for Fine-grained and Domain-adaptive Recognition of Cereal Grains
- Connecting Neural Response measurements & Computational Models of language: a non-comprehensive guide
- BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis
- Domain Generalisation for Object Detection under Covariate and Concept Shift
- Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework
- Contrastive Boundary Learning for Point Cloud Segmentation
- Real-time Scene Text Detection Based on Global Level and Word Level Features
- A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach
- Conditional Synthetic Data Generation for Personal Thermal Comfort Models
- Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement
- Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods
- Similarity-based Label Inference Attack against Training and Inference of Split Learning
- Transferring Dual Stochastic Graph Convolutional Network for Facial Micro-expression Recognition
- ReF -- Rotation Equivariant Features for Local Feature Matching
- Crowd Source Scene Change Detection and Local Map Update
- MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes
- Online Deep Metric Learning via Mutual Distillation
- Hyperspectral Imaging for cherry tomato
- A Screen-Shooting Resilient Document Image Watermarking Scheme using Deep Neural Network
- Bayesian Spatial Predictive Synthesis
- A Review of Open Source Software Tools for Time Series Analysis
- Learning Torque Control for Quadrupedal Locomotion
- Adaptive Background Matting Using Background Matching
- A Systematic Literature Review on Blockchain Enabled Federated Learning Framework for Internet of Vehicles
- NeRFocus: Neural Radiance Field for 3D Synthetic Defocus
- Cluttered Food Grasping with Adaptive Fingers and Synthetic-Data Trained Object Detection
- Towards Open-Set Text Recognition via Label-to-Prototype Learning
- An Audio-Visual Attention Based Multimodal Network for Fake Talking Face Videos Detection
- MVP: Multimodality-guided Visual Pre-training
- Assessing Phenotype Definitions for Algorithmic Fairness
- TextConvoNet:A Convolutional Neural Network based Architecture for Text Classification
- TiSAT: Time Series Anomaly Transformer
- Discrepancy Modeling Framework: Learning missing physics, modeling systematic residuals, and disambiguating between deterministic and random effects
- End-to-End Semantic Video Transformer for Zero-Shot Action Recognition
- Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack
- Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity
- An Accurate Unsupervised Method for Joint Entity Alignment and Dangling Entity Detection
- Cascaded Sparse Feature Propagation Network for Interactive Segmentation
- IAE-Net: Integral Autoencoders for Discretization-Invariant Learning
- Speciesist Language and Nonhuman Animal Bias in English Masked Language Models
- Cross-modal Map Learning for Vision and Language Navigation
- Manifold Modeling in Quotient Space: Learning An Invariant Mapping with Decodability of Image Patches
- Compilable Neural Code Generation with Compiler Feedback
- Action-Constrained Reinforcement Learning for Frame-Level Bit Allocation in HEVC/H.265 through Frank-Wolfe Policy Optimization
- PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks
- Multi-Task Adversarial Learning for Treatment Effect Estimation in Basket Trials
- DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting
- Collusion Detection in Team-Based Multiplayer Games
- A low-rank ensemble Kalman filter for elliptic observations
- MetAug: Contrastive Learning via Meta Feature Augmentation
- Semi-supervision semantic segmentation with uncertainty-guided self cross supervision
- Optimal Methods for Convex Risk Averse Distributed Optimization
- Internet-augmented language models through few-shot prompting for open-domain question answering
- OpenTAL: Towards Open Set Temporal Action Localization
- Librarian-in-the-Loop: A Natural Language Processing Paradigm for Detecting Informal Mentions of Research Data in Academic Literature
- Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models
- Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGA
- A Tree-Structured Multi-Task Model Recommender